v4 GRE: Add TCP segmentation offload for GRE

Following patch adds GRE protocol offload handler so that
skb_gso_segment() can segment GRE packets.
SKB GSO CB is added to keep track of total header length so that
skb_segment can push entire header. e.g. in case of GRE, skb_segment
need to push inner and outer headers to every segment.
New NETIF_F_GRE_GSO feature is added for devices which support HW
GRE TSO offload. Currently none of devices support it therefore GRE GSO
always fall backs to software GSO.

[ Compute pkt_len before ip_local_out() invocation. -DaveM ]

Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 118 insertions, 0 deletions

diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
index 42a491055c76..7a4c710c4cdd 100644
--- a/net/ipv4/gre.c
+++ b/net/ipv4/gre.c
@@ -19,6 +19,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/netdevice.h>
+#include <linux/if_tunnel.h>
 #include <linux/spinlock.h>
 #include <net/protocol.h>
 #include <net/gre.h>
@@ -26,6 +27,11 @@
 
 static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
 static DEFINE_SPINLOCK(gre_proto_lock);
+struct gre_base_hdr {
+        __be16 flags;
+        __be16 protocol;
+};
+#define GRE_HEADER_SECTION 4
 
 int gre_add_protocol(const struct gre_protocol *proto, u8 version)
 {
@@ -112,12 +118,117 @@ static void gre_err(struct sk_buff *skb, u32 info)
         rcu_read_unlock();
 }
 
+static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
+                                       netdev_features_t features)
+{
+        struct sk_buff *segs = ERR_PTR(-EINVAL);
+        netdev_features_t enc_features;
+        int ghl = GRE_HEADER_SECTION;
+        struct gre_base_hdr *greh;
+        int mac_len = skb->mac_len;
+        int tnl_hlen;
+        bool csum;
+
+        if (unlikely(skb_shinfo(skb)->gso_type &
+                                ~(SKB_GSO_TCPV4 |
+                                  SKB_GSO_TCPV6 |
+                                  SKB_GSO_UDP |
+                                  SKB_GSO_DODGY |
+                                  SKB_GSO_TCP_ECN |
+                                  SKB_GSO_GRE)))
+                goto out;
+
+        if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
+                goto out;
+
+        greh = (struct gre_base_hdr *)skb_transport_header(skb);
+
+        if (greh->flags & GRE_KEY)
+                ghl += GRE_HEADER_SECTION;
+        if (greh->flags & GRE_SEQ)
+                ghl += GRE_HEADER_SECTION;
+        if (greh->flags & GRE_CSUM) {
+                ghl += GRE_HEADER_SECTION;
+                csum = true;
+        } else
+                csum = false;
+
+        /* setup inner skb. */
+        if (greh->protocol == htons(ETH_P_TEB)) {
+                struct ethhdr *eth = eth_hdr(skb);
+                skb->protocol = eth->h_proto;
+        } else {
+                skb->protocol = greh->protocol;
+        }
+
+        skb->encapsulation = 0;
+
+        if (unlikely(!pskb_may_pull(skb, ghl)))
+                goto out;
+        __skb_pull(skb, ghl);
+        skb_reset_mac_header(skb);
+        skb_set_network_header(skb, skb_inner_network_offset(skb));
+        skb->mac_len = skb_inner_network_offset(skb);
+
+        /* segment inner packet. */
+        enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+        segs = skb_mac_gso_segment(skb, enc_features);
+        if (!segs || IS_ERR(segs))
+                goto out;
+
+        skb = segs;
+        tnl_hlen = skb_tnl_header_len(skb);
+        do {
+                __skb_push(skb, ghl);
+                if (csum) {
+                        __be32 *pcsum;
+
+                        if (skb_has_shared_frag(skb)) {
+                                int err;
+
+                                err = __skb_linearize(skb);
+                                if (err) {
+                                        kfree_skb(segs);
+                                        segs = ERR_PTR(err);
+                                        goto out;
+                                }
+                        }
+
+                        greh = (struct gre_base_hdr *)(skb->data);
+                        pcsum = (__be32 *)(greh + 1);
+                        *pcsum = 0;
+                        *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
+                }
+                __skb_push(skb, tnl_hlen - ghl);
+
+                skb_reset_mac_header(skb);
+                skb_set_network_header(skb, mac_len);
+                skb->mac_len = mac_len;
+        } while ((skb = skb->next));
+out:
+        return segs;
+}
+
+static int gre_gso_send_check(struct sk_buff *skb)
+{
+        if (!skb->encapsulation)
+                return -EINVAL;
+        return 0;
+}
+
 static const struct net_protocol net_gre_protocol = {
         .handler     = gre_rcv,
         .err_handler = gre_err,
         .netns_ok    = 1,
 };
 
+static const struct net_offload gre_offload = {
+        .callbacks = {
+                .gso_send_check =       gre_gso_send_check,
+                .gso_segment    =       gre_gso_segment,
+        },
+};
+
 static int __init gre_init(void)
 {
         pr_info("GRE over IPv4 demultiplexor driver\n");
@@ -127,11 +238,18 @@ static int __init gre_init(void)
                 return -EAGAIN;
         }
 
+        if (inet_add_offload(&gre_offload, IPPROTO_GRE)) {
+                pr_err("can't add protocol offload\n");
+                inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
+                return -EAGAIN;
+        }
+
         return 0;
 }
 
 static void __exit gre_exit(void)
 {
+        inet_del_offload(&gre_offload, IPPROTO_GRE);
         inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
 }